Industrial and medical anomaly detection through cycle-consistent adversarial networks

Arnaud Bougaham, Valentin Delchevalerie, Mohammed El Adoui, Benoît Frénay

Abstract: Highlights•Use abnormal data through a Cycle-GAN for AD, for better discrimination.•Provide intuition on why the identity loss are meaningful for AD.•Discuss the performances for diverse industrial and medical AD problems.•Conduct an extensive benchmark to compare the proposed approach with SOTA methods.•Discuss why Cycle-GAN is well suited for AD in specific image types.